DPDK patches and discussions
 help / color / mirror / Atom feed
From: Maxime Coquelin <maxime.coquelin@redhat.com>
To: Stefan Hajnoczi <stefanha@redhat.com>, dev@dpdk.org
Cc: Yuanhan Liu <yliu@fridaylinux.org>,
	wei.w.wang@intel.com, mst@redhat.com,  zhiyong.yang@intel.com,
	jasowang@redhat.com
Subject: Re: [dpdk-dev] [RFC 23/24] WORKAROUND revert virtio-net mq vring deletion
Date: Tue, 30 Jan 2018 18:52:42 +0100	[thread overview]
Message-ID: <d496e1b8-23ff-fb1e-0e67-ef9f7fc7b27e@redhat.com> (raw)
In-Reply-To: <20180119134444.24927-24-stefanha@redhat.com>

Hi Stefan,

On 01/19/2018 02:44 PM, Stefan Hajnoczi wrote:
> The virtio-net mq vring deletion code should be in virtio_net.c, not in
> the generic vhost_user.c code where it breaks non-virtio-net devices.
> 
> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> ---
>   drivers/librte_vhost/vhost_user.c | 2 ++
>   1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/librte_vhost/vhost_user.c b/drivers/librte_vhost/vhost_user.c
> index a819684b4..08fab933b 100644
> --- a/drivers/librte_vhost/vhost_user.c
> +++ b/drivers/librte_vhost/vhost_user.c
> @@ -163,6 +163,7 @@ vhost_user_set_features(struct virtio_net *dev, uint64_t features)
>   		(dev->features & (1 << VIRTIO_NET_F_MRG_RXBUF)) ? "on" : "off",
>   		(dev->features & (1ULL << VIRTIO_F_VERSION_1)) ? "on" : "off");
>   
> +#if 0
>   	if (!(dev->features & (1ULL << VIRTIO_NET_F_MQ))) {
>   		/*
>   		 * Remove all but first queue pair if MQ hasn't been
> @@ -181,6 +182,7 @@ vhost_user_set_features(struct virtio_net *dev, uint64_t features)
>   			free_vq(vq);
>   		}
>   	}
> +#endif
>   
>   	return 0;
>   }
> 

Thanks for reporting the issue.
It seems difficult to move this check in virtio-net.c without a deep
rework.

But I think we can workaround by ensuring the backend supports
VIRTIO_NET_F_MQ, but it has not been negotiated.
Something like:

if ((vhost_features & (1ULL << VIRTIO_NET_F_MQ)) &&
	!(dev->features & (1ULL << VIRTIO_NET_F_MQ)) {
...
}

Any thoughts?

Thanks,
Maxime

  reply	other threads:[~2018-01-30 17:52 UTC|newest]

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-01-19 13:44 [dpdk-dev] [RFC 00/24] vhost: add virtio-vhost-user transport Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 01/24] vhost: move vring_call() into trans_af_unix.c Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 02/24] vhost: move AF_UNIX code from socket.c to trans_af_unix.c Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 03/24] vhost: allocate per-socket transport state Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 04/24] vhost: move socket_fd and un sockaddr into trans_af_unix.c Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 05/24] vhost: move start_server/client() calls to trans_af_unix.c Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 06/24] vhost: move vhost_user_connection " Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 07/24] vhost: move vhost_user_reconnect_init() into trans_af_unix.c Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 08/24] vhost: move vhost_user.fdset to trans_af_unix.c Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 09/24] vhost: pass vhost_transport_ops through vhost_new_device() Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 10/24] vhost: embed struct virtio_net inside struct vhost_user_connection Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 11/24] vhost: extract vhost_user.c socket I/O into transport Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 12/24] vhost: move slave_req_fd field to AF_UNIX transport Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 13/24] vhost: move mmap/munmap " Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 14/24] vhost: move librte_vhost to drivers/ Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 15/24] vhost: add virtio pci framework Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 16/24] vhost: remember a vhost_virtqueue's queue index Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 17/24] vhost: add virtio-vhost-user transport Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 18/24] vhost: add RTE_VHOST_USER_VIRTIO_TRANSPORT flag Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 19/24] net/vhost: add virtio-vhost-user support Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 20/24] examples/vhost_scsi: add --socket-file argument Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 21/24] examples/vhost_scsi: add virtio-vhost-user support Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 22/24] usertools: add virtio-vhost-user devices to dpdk-devbind.py Stefan Hajnoczi
2018-01-19 13:44 ` [dpdk-dev] [RFC 23/24] WORKAROUND revert virtio-net mq vring deletion Stefan Hajnoczi
2018-01-30 17:52   ` Maxime Coquelin [this message]
2018-01-19 13:44 ` [dpdk-dev] [RFC 24/24] WORKAROUND examples/vhost_scsi: avoid broken EVENT_IDX Stefan Hajnoczi
2018-01-19 19:31   ` Michael S. Tsirkin
2018-01-31 10:02 ` [dpdk-dev] [RFC 00/24] vhost: add virtio-vhost-user transport Maxime Coquelin
     [not found] ` <20180410093847.GA22081@stefanha-x1.localdomain>
2018-04-10 14:56   ` Wang, Wei W

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=d496e1b8-23ff-fb1e-0e67-ef9f7fc7b27e@redhat.com \
    --to=maxime.coquelin@redhat.com \
    --cc=dev@dpdk.org \
    --cc=jasowang@redhat.com \
    --cc=mst@redhat.com \
    --cc=stefanha@redhat.com \
    --cc=wei.w.wang@intel.com \
    --cc=yliu@fridaylinux.org \
    --cc=zhiyong.yang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).